© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50122
    Prev
    Next
    INDEX
    Explanations

    19th and 20th centuries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsequent
    -0.09
     తరువాత
    -0.09
     senere
    -0.09
     Vanaf
    -0.09
     posteriormente
    -0.09
     وروسته
    -0.09
    later
    -0.09
     futura
    -0.09
     póź
    -0.09
     ileri
    -0.09
    POSITIVE LOGITS
     antiqu
    0.09
     teens
    0.09
     mån
    0.08
    还是
    0.08
    's
    0.08
    」を
    0.08
    を
    0.08
    冬
    0.07
    ’s
    0.07
    ‘s
    0.07
    Activations Density 0.018%

    No Known Activations